List: General Discussion « Previous MessageNext Message » From: Christopher R. Jones Date: March 11 2000 3:38pm Subject: Re: standard deviation View as plain text
```Excel does offer 2 functions, one for sample standard deviation and the
other for population standard deviation.
>
>That depends on the purpose you have in mind.  If you have a known
>distribution, you use the population standard deviation, meaning sqrt of
>variance over N.  If you are attempting to measure the stddev from a sample
>of random data, determining the mean takes one of your degrees of freedom,
>so you divide by N-1.  To illustrate, if you are calculating the "standard
>deviation" (it's not a normal distribution, so the utility of such a measure
>is unclear, but that never stopped a statistician ;) of the probability
>distribution describing the sum of a pair of dice, you divide the variance
>by 36 (the number of distinct possibilities).  If you throw a pair of dice
>36 times and collect the results, you should divide the variance by 35.
>
>As someone who knows and cares about such things, I feel that MySQL (and
>Perl and Excel and the rest), should, like a good scientific calculator,
>offer both functions.
>
>
>Ryan Caveney
>
>
>
>--
>---------------------------------------------------------------------
>Please check "http://www.mysql.com/Manual_chapter/manual_toc.html" before
>posting. To request this thread, e-mail mysql-thread30831@stripped
>
>To unsubscribe, send a message to:
>    <mysql-unsubscribe-cj=interlog.com@stripped>
>
>
>
Christopher R. Jones, P.Eng.
14 Oneida Avenue
Toronto, Ontario M5J 2E3
Tel. 416 203-7465
Fax. 416 203-3044
Email cj@stripped

```
Thread
standard deviationlearning user4 Mar
• Re: standard deviationsasha9 Mar
Re: standard deviationlearning user10 Mar
Re: standard deviationRyan Caveney10 Mar
Re: standard deviationChristopher R. Jones11 Mar
Re: standard deviationlearning user12 Mar
• Re: standard deviationsasha12 Mar
Re: standard deviationlearning user13 Mar